M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

Compare scores, permissions, risks, and fit in one decision-focused table.

DimensionAtlassian Bitbucket MCP ServerConnect AI to Your Bitbucket RepositoriesMartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS56 / 100 · C79 / 100 · B
Reliability8 / 2012 / 20
Security and permissions10 / 2018 / 20
Maintenance10 / 2016 / 20
Documentation16 / 2018 / 20
Setup experience12 / 2015 / 20
Best for
  • Developers who want AI assistance with code reviews and repository management.
  • Team leads needing quick insights into project status and pull request activity.
  • DevOps engineers automating repository workflows and branch management.
  • Anyone who wants to interact with Bitbucket using natural language.
  • Engineering teams scaling AI coding agents while controlling spend
  • Platform teams that need auditable, rollback-aware agent execution records
  • Organizations using multiple agents (Claude, Codex, Gemini) under one governed flow
Not for
  • Users of Bitbucket Server or Data Center (only Bitbucket Cloud is supported).
  • Users needing real-time push or continuous connections (request-response only).
  • Those requiring complex operations beyond the Bitbucket REST API 2.0 scope.
  • Users unwilling to handle JSON or TOON output (default is TOON, can override to JSON).
  • Developers who just want a simple code-completion helper without run governance
  • Teams unwilling to accept local JSONL run records with HMAC signing
  • Environments without a supported adapter (Claude/Codex/Gemini CLIs, direct provider, or verifier-only)
Required permissions
  • Requires Bitbucket authentication credentials: Atlassian API token (recommended) or app password (legacy).
  • Appropriate permission scopes: repository and workspace for read-only; add pullrequest for PR management.
  • For app passwords: Workspaces: Read, Repositories: Read (add Write for mutations), Pull Requests: Read (add Write for PR management).
  • Local file system write access if you intend to clone repositories.
  • Read/write access to the configured repo root (writable scope restrictable via --allow-path/--deny-path)
  • Ability to invoke the chosen agent CLI (Claude/Codex/Gemini, etc.) and its underlying model account
  • Local disk writes for run records, receipts, and share outputs (share/run-receipt., etc.)
  • Execution of user-configured verifier commands (e.g. npm test)
Risks and side effects
  • Credential exposure: Tokens or passwords stored in environment variables could be accessed by unauthorized parties. Keep them secure and rotate regularly.
  • Data access: The server can access all Bitbucket data you grant permission to, including private repositories. Run only in trusted environments.
  • Token consumption: Unfiltered API responses can be large, leading to high token costs. Always use JMESPath filtering and pagination.
  • Accidental mutations: AI could perform unintended operations via POST/PUT/PATCH/DELETE tools (e.g., merge PR, delete branch). Test in read-only mode first.
  • Dependency risk: Using npx runs the latest version, which may introduce breaking changes. Consider pinning a version.
  • Verifier commands are executed; poorly chosen verifier commands carry security risk despite preflight policy checks
  • Cost and token figures may be estimates (labeled with provenance) and should not be treated as settled accounting
  • Receipt integrity must be verified before use as trustworthy evidence; missing rollback evidence is flagged as EVIDENCE_BOUNDARY
  • Policy defaults come from martin.config.yaml and can be overridden by CLI flags; misconfiguration can loosen safety boundaries
Supported clientsClaude Desktop, Cursor AI, Continue, ClineClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools60